Acoustic data-driven grapheme-to-phoneme conversion using KL-HMM.
Ramya RasipuramMathew Magimai-DossPublished in: ICASSP (2012)
Keyphrases
- feature selection
- data driven
- grapheme to phoneme conversion
- hidden markov models
- natural language processing
- speaker independent
- language resources
- speech recognition
- text classification
- acoustic features
- kullback leibler
- machine learning
- speech signal
- speech recognition systems
- automatic speech recognition
- kl divergence
- machine translation
- cross language information retrieval
- multi modal
- natural language